.png){kind=icon}
返回
Differentially private Riemannian optimization
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-023-06508-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we study the differentially private empirical risk minimization problem where the parameter is constrained to a Riemannian manifold. We introduce a framework for performing differentially private Riemannian optimization by adding noise to the Riemannian gradient on the tangent space. The noise follows a Gaussian distribution intrinsically defined with respect to the Riemannian metric on the tangent space. We adapt the Gaussian mechanism from the Euclidean space to the tangent space compatible to such generalized Gaussian distribution. This approach presents a novel analysis as compared to directly adding noise on the manifold. We further prove privacy guarantees of the proposed differentially private Riemannian (stochastic) gradient descent using an extension of the moments accountant technique. Overall, we provide utility guarantees under geodesic (strongly) convex, general nonconvex objectives as well as under the Riemannian Polyak-Lojasiewicz condition. Empirical results illustrate the versatility and efficacy of the proposed framework in several applications.
Keyword:
Riemannian manifold
Riemannian optimization
Stochastic optimization
Differential privacy
Empirical risk minimization
Tangent Gaussian
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
The relationship of monodentate and bidentate coordinated uranium(VI) sulfate in aqueous solution
.png){kind=icon}
PREAI
分享收藏
分享收藏
查看更多内容